VLM Evaluation

VLM: Vision-Language Model

Follow this topic Ask about this topic

Vision-language model evaluation studies what these systems can infer from images and video, and whether their answers are supported by visual evidence. Researchers use broad benchmarks alongside controlled probes, counterfactual edits, and stage-wise tests covering tasks such as spatial reasoning, charts and documents, medical imaging, and long-video understanding. They assess not only accuracy but also grounding, hallucination, calibration, robustness, bias, and abstention, often comparing models with human or specialist judgments. A central challenge is that high benchmark scores can reflect language priors or shortcuts rather than reliable visual understanding, and performance often falters on fine-grained, temporal, compositional, or unfamiliar tasks.

Latest papers

999 papers122 papers in the last four weeks, up 12% on the four weeks before. 0.7% of all new papers.

Feb 27, 2026

Shape vs. Context: Examining Human--AI Gaps in Ambiguous Japanese Character Recognition

High text recognition performance does not guarantee that Vision-Language Models (VLMs) share human-like decision patterns when resolving ambiguity. We investigate this behavioral gap by directly comparing humans and VLMs using continuously interpolated Japanese character shapes generated via a

β

-VAE. We estimate decision boundaries in a single-character recognition (shape-only task) and evaluate whether VLM responses align with human judgments under shape in context (i.e., embedding an ambiguous character near the human decision boundary in word-level context). We find that human and VLM decision boundaries differ in the shape-only task, and that shape in context can improve human alignment in some conditions. These results highlight qualitative behavioral differences, offering foundational insights toward human--VLM alignment benchmarking.

Daichi Haraguchi

CyberAgent, Tokyo, Japan

VLM Evaluation Vision-Language Alignment Optical Character Recognition

Feb 26, 2026

SUPERGLASSES: Benchmarking Vision Language Models as Intelligent Agents for AI Smart Glasses

The rapid advancement of AI-powered smart glasses-one of the hottest wearable devices-has unlocked new frontiers for multimodal interaction, with Visual Question Answering (VQA) over external knowledge sources emerging as a core application. Existing Vision Language Models (VLMs) adapted to smart glasses are typically trained and evaluated on traditional multimodal datasets; however, these datasets lack the variety and realism needed to reflect smart glasses usage scenarios and diverge from their specific challenges, where accurately identifying the object of interest must precede any external knowledge retrieval. To bridge this gap, we introduce SUPER- GLASSES, the first comprehensive VQA benchmark built on real-world data entirely collected by smart glasses devices. SUPERGLASSES comprises 2,422 egocentric image-question pairs spanning 14 image domains and 8 query categories, enriched with full search trajectories and reasoning annotations. We evaluate 26 representative VLMs on this benchmark, revealing significant performance gaps. To address the limitations of existing models, we further propose the SUPERLENS, a multimodal smart glasses agent that enables retrieval-augmented answer generation by integrating automatic object detection, query decoupling, and multimodal web search. SUPERLENS achieves state-of-the-art performance, outperforming GPT-4o by 2.19%, underscoring the need for task-specific solutions in smart glasses VQA. Our dataset is publicly available at https://huggingface.co/datasets/xandery/SuperGlasses.

Zhuohang Jiang, Xu Yuan, Haohao Qu +4

The Hong Kong Polytechnic University

Visual Question Answering Knowledge-Based VQA VLM Evaluation Tool-Using Vision-Language Agents

Feb 24, 2026

PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models

Medical Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, a failure mode that threatens deployment safety. We introduce PSF-Med, a benchmark of 26,850 chest X-ray questions paired with 92,856 meaning-preserving paraphrases across MIMIC-CXR, PadChest, and VinDr-CXR, spanning clinical populations in the US, Spain, and Vietnam. Every paraphrase is validated by an LLM judge using a bidirectional clinical entailment rubric, with 91.6% cross-family agreement. Across nine VLMs, including general-purpose models, we find flip rates from 3% to 37%. However, low flip rate does not imply visual grounding: text-only baselines show that some models stay consistent even when the image is removed, suggesting they rely on language priors. To study mechanisms in one model, we apply GemmaScope 2 Sparse Autoencoders (SAEs) to MedGemma 4B and analyze FlipBank, a curated set of 158 flip cases. We identify a sparse feature at layer 17 that correlates with prompt framing and predicts decision margin shifts. In causal patching, removing this feature's contribution recovers 45% of the yes-minus-no logit margin on average and fully reverses 15% of flips. Acting on this finding, we show that clamping the identified feature at inference reduces flip rates by 31% relative with only a 1.3 percentage-point accuracy cost, while also decreasing text-prior reliance. These results suggest that flip rate alone is not enough; robustness evaluations should test both paraphrase stability and image reliance.

Binesh Sadanandan, Vahid Behzadan

SAIL Lab, University of New Haven, West Haven, CT, USA.

Medical VLMs VLM Evaluation VLM Robustness VLM Interpretability

Feb 24, 2026

VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation

Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's ability to estimate the correctness of its own outputs, which can improve deployment reliability; however, they depend heavily on language priors and are therefore ill-suited for evaluating vision-conditioned predictions. We propose VAUQ, a vision-aware uncertainty quantification framework for LVLM self-evaluation that explicitly measures how strongly a model's output depends on visual evidence. VAUQ introduces the Image-Information Score (IS), which captures the reduction in predictive uncertainty attributable to visual input, and an unsupervised core-region masking strategy that amplifies the influence of salient regions. Combining predictive entropy with this core-masked IS yields a training-free scoring function that reliably reflects answer correctness. Comprehensive experiments show that VAUQ consistently outperforms existing self-evaluation methods across multiple datasets.

Seongheon Park, Changdae Oh, Hyeong Kyu Choi +2

University of Wisconsin-Madison · Nanyang Technological University

Confidence Estimation for VLMs VLM Evaluation Hallucination Detection in VLMs

Feb 24, 2026

Diagnosing Causal Reasoning in Vision-Language Models via Structured Relevance Graphs

Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of the answers, making it unclear whether failures arise from limited reasoning capability or from misidentifying causally relevant information. We introduce Vision-Language Causal Graphs (VLCGs), a structured, query-conditioned representation that explicitly encodes causally relevant objects, attributes, relations, and scene-grounded assumptions. Building on this representation, we present ViLCaR, a diagnostic benchmark comprising tasks for Causal Attribution, Causal Inference, and Question Answering, along with graph-aligned evaluation metrics that assess relevance identification beyond final answer accuracy. Experiments in state-of-the-art LVLMs show that injecting structured relevance information significantly improves attribution and inference consistency compared to zero-shot and standard in-context learning. These findings suggest that current limitations in LVLM causal reasoning stem primarily from insufficient structural guidance rather than a lack of reasoning capacity.

Dhita Putri Pratama, Soyeon Caren Han, Yihao Ding

University of Melbourne Melbourne, Australia · The University of Western Australia Perth, Australia

VLM Reasoning VLM Evaluation Large Vision-Language Models Causal Attribution

Feb 24, 2026

How Foundational Skills Influence VLM-based Embodied Agents:A Native Perspective

Recent advances in vision-language models (VLMs) have shown promise for human-level embodied intelligence. However, existing benchmarks for VLM-driven embodied agents often rely on high-level commands or discretized action spaces, which are non-native settings that differ markedly from real-world control. In addition, current benchmarks focus primarily on high-level tasks and lack joint evaluation and analysis at both low and high levels. To address these limitations, we present NativeEmbodied, a challenging benchmark for VLM-driven embodied agents that uses a unified, native low-level action space. Built on diverse simulated scenes, NativeEmbodied includes three representative high-level tasks in complex scenarios to evaluate overall performance. For more detailed analysis, we further decouple the skills required by complex tasks and construct four types of low-level tasks, each targeting a fundamental embodied skill. This joint evaluation across task and skill granularities enables fine-grained assessment of embodied agents. Experiments with state-of-the-art VLMs reveal clear deficiencies in several fundamental embodied skills, and further analysis shows that these bottlenecks significantly limit performance on high-level tasks. NativeEmbodied highlights key challenges for current VLM-driven embodied agents and provides insights to guide future research.

Bo Peng, Pi Bu, Keyu Pan +7

University of Science and Technology of China · Alibaba Group · Independent Researcher +1

Embodied Agent Benchmarks Embodied AI Vision-Language Agents VLM Evaluation Robotic Control

Feb 24, 2026

How Do Inpainting Artifacts Propagate to Language?

We study how visual artifacts introduced by diffusion-based inpainting affect language generation in vision-language models. We use a two-stage diagnostic setup in which masked image regions are reconstructed and then provided to captioning models, enabling controlled comparisons between captions generated from original and reconstructed inputs. Across multiple datasets, we analyze the relationship between reconstruction fidelity and downstream caption quality. We observe consistent associations between pixel-level and perceptual reconstruction metrics and both lexical and semantic captioning performance. Additional analysis of intermediate visual representations and attention patterns shows that inpainting artifacts lead to systematic, layer-dependent changes in model behavior. Together, these results provide a practical diagnostic framework for examining how visual reconstruction quality influences language generation in multimodal systems.

Pratham Yashwante, Davit Abrahamyan, Shresth Grover +1

UC San Diego

VLM Robustness VLM Evaluation Image Inpainting Image Captioning

Feb 23, 2026

Do Large Language Models Understand Data Visualization Principles?

Data visualization principles, derived from decades of research in design and perception, ensure proper visual communication. While prior work has shown that large language models (LLMs) can generate charts or flag misleading figures, it remains unclear whether they and their vision-language counterparts (VLMs) can reason about and enforce visualization principles directly. Constraint based systems encode these principles as logical rules for precise automated checks, but translating them into formal specifications demands expert knowledge. This motivates leveraging LLMs and VLMs as principle checkers that can reason about visual design directly, bypassing the need for symbolic rule specification. In this paper, we present the first systematic evaluation of both LLMs and VLMs on their ability to reason about visualization principles, using hard verification ground truth derived from Answer Set Programming (ASP). We compiled a set of visualization principles expressed as natural-language statements and generated a controlled dataset of approximately 2,000 Vega-Lite specifications annotated with explicit principle violations, complemented by over 300 real-world Vega-Lite charts. We evaluated both checking and fixing tasks, assessing how well models detect principle violations and correct flawed chart specifications. Our work highlights both the promise of large (vision-)language models as flexible validators and editors of visualization designs and the persistent gap with symbolic solvers on more nuanced aspects of visual perception. They also reveal an interesting asymmetry: frontier models tend to be more effective at correcting violations than at detecting them reliably.

Martin Sinnona, Valentin Bonas, Viviana Siless +1

Universidad Torcuato Di Tella, Buenos Aires, Argentina · Universidad de Buenos Aires, Buenos Aires, Argentina · Consejo Nacional de Investigaciones Científicas y Técnicas, Buenos Aires, Argentina

LLM Evaluation VLM Evaluation

Feb 22, 2026

VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing

We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, complex editing, and visual understanding. VectorGym addresses the lack of realistic, challenging benchmarks aligned with professional design workflows. Our benchmark comprises four tasks with expert human-authored annotations: the novel Sketch2SVG task (VG-Sketch); a new SVG editing dataset (VG-Edit) featuring complex, multi-step edits with higher-order primitives; Text2SVG generation (VG-Text); and SVG captioning (VG-Cap). Unlike prior benchmarks that rely on synthetic edits, VectorGym provides gold-standard human annotations that require semantic understanding and design intent. We also provide a multi-task reinforcement learning baseline that jointly optimizes across all four tasks using rendering-based rewards. This baseline, built on GRPO with curriculum learning, trains a Qwen3-VL 8B model that achieves state-of-the-art performance among open-source models, surpassing much larger models including Qwen3-VL 235B and matching GPT-4o. We also introduce a VLM-as-a-Judge metric for SVG generation, validated through human correlation studies. Our evaluation of frontier VLMs reveals significant performance gaps, positioning VectorGym as a rigorous framework for advancing visual code generation.

Joan Rodriguez, Haotian Zhang, Abhay Puri +14

Mila, Quebec AI Institute · ÉTS Montréal · QuiverAI +11

VLM Evaluation Code Generation Image Editing Code Generation Benchmarks Vector Graphics Generation Text-to-SVG Generation

Feb 21, 2026

MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment

Fine-grained image-caption alignment is crucial for vision-language models (VLMs), especially in socially critical contexts such as identifying real-world risk scenarios or distinguishing cultural proxies, where correct interpretation hinges on subtle visual or linguistic clues and where minor misinterpretations can lead to significant real-world consequences. We present MiSCHiEF, a set of two benchmarking datasets based on a contrastive pair design in the domains of safety (MiS) and culture (MiC), and evaluate four VLMs on tasks requiring fine-grained differentiation of paired images and captions. In both datasets, each sample contains two minimally differing captions and corresponding minimally differing images. In MiS, the image-caption pairs depict a safe and an unsafe scenario, while in MiC, they depict cultural proxies in two distinct cultural contexts. We find that models generally perform better at confirming the correct image-caption pair than rejecting incorrect ones. Additionally, models achieve higher accuracy when selecting the correct caption from two highly similar captions for a given image, compared to the converse task. The results, overall, highlight persistent modality misalignment challenges in current VLMs, underscoring the difficulty of precise cross-modal grounding required for applications with subtle semantic and visual distinctions.

Sagarika Banerjee, Tangatar Madi, Advait Swaminathan +4

Algoverse AI Research · PocketFM

Cultural Safety Evaluation of VLMs VLM Evaluation Text-Image Alignment Vision-Language Models Modality Gap in VLMs

Feb 20, 2026

OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models

Existing Visual-Language Models (VLMs) have achieved significant progress by being trained on massive-scale datasets, typically under the assumption that data are independent and identically distributed (IID). However, in real-world scenarios, it is often impractical to expect that all data processed by an AI system satisfy this assumption. Furthermore, failure to appropriately handle out-of-distribution (OOD) objects may introduce safety risks in real-world applications (e.g., autonomous driving or medical assistance). Unfortunately, current research has not yet provided valid benchmarks that can comprehensively assess the performance of VLMs in response to OOD data. Therefore, we propose OODBench, a predominantly automated method with minimal human verification, for constructing new benchmarks and evaluating the ability of VLMs to process OOD data. OODBench contains 40K instance-level OOD instance-category pairs, and we show that current VLMs still exhibit notable performance degradation on OODBench, even when the underlying image categories are common. In addition, we propose a reliable automated assessment metric that employs a Basic-to-Advanced Progression of prompted questions to assess the impact of OOD data on questions of varying difficulty more fully. Lastly, we summarize substantial findings and insights to facilitate future research in the acquisition and evaluation of OOD data.

Ling Lin, Yang Bai, Heng Su +5

School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei 230000, China · Suzhou Institute for Advanced Research, USTC, Suzhou 215123, China · Institute of High Performance Computing (IHPC), A*STAR, Singapore +1

VLM Evaluation VLM Robustness OOD Generalization Large Vision-Language Models

Feb 19, 2026

Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models

Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and multimodal dialogue. These improvements are evident in a wide range of VLMs built on a variety of base models, alignment architectures, and training data. However, recent works show that these models trail behind in traditional image classification benchmarks, which test fine-grained visual knowledge. We test a large number of recent VLMs on fine-grained classification benchmarks and identify potential factors in the disconnect between fine-grained knowledge and other vision benchmarks. Through a series of ablation experiments, we find that using a better LLM improves all benchmark scores equally, while a better vision encoder disproportionately improves fine-grained classification performance. Furthermore, we find that the pretraining stage is also vital to fine-grained performance, particularly when the language model weights are unfrozen during pretraining. These insights pave the way for enhancing fine-grained visual understanding and vision-centric capabilities in VLMs.

Dhruba Ghosh, Yuhui Zhang, Ludwig Schmidt

Stanford University

Fine-Grained Visual Perception VLM Evaluation Fine-Grained Image Classification Vision-Language Pretraining

Feb 19, 2026

Sketch2Feedback: Grammar-in-the-Loop Framework for Rubric-Aligned Feedback on Student STEM Diagrams

Providing timely, rubric-aligned feedback on student-drawn diagrams is a persistent challenge in STEM education. While large multimodal models (LMMs) can jointly parse images and generate explanations, their tendency to hallucinate undermines trust in classroom deployments. We present Sketch2Feedback, a grammar-in-the-loop framework that decomposes the problem into four stages -- hybrid perception, symbolic graph construction, constraint checking, and constrained VLM feedback -- so that the language model verbalizes only violations verified by an upstream rule engine. We evaluate on two synthetic micro-benchmarks, FBD-10 (free-body diagrams) and Circuit-10 (circuit schematics), each with 500 images spanning standard and hard noise augmentation tiers, comparing our pipeline against end-to-end LMMs (LLaVA-1.5-7B, Qwen2-VL-7B), a vision-only detector, a YOLOv8-nano learned detector, and an ensemble oracle. On n=100 test samples per benchmark with 95% bootstrap CIs, results are mixed and instructive: Qwen2-VL-7B achieves the highest micro-F1 on both FBDs (0.570) and circuits (0.528), but with extreme hallucination rates (0.78, 0.98). An ensemble oracle that selects the best prediction per sample reaches F1=0.556 with hallucination 0.320 on FBDs, demonstrating exploitable complementarity between grammar and end-to-end approaches. Confidence thresholding at tau=0.7 reduces circuit hallucination from 0.970 to 0.880 with no F1 loss. Hard noise augmentation reveals domain-dependent robustness: FBD detection is resilient while circuit detection degrades sharply. An LLM-as-judge evaluation confirms that the grammar pipeline produces more actionable circuit feedback (4.85/5) than the end-to-end LMM (3.11/5). We release all code, datasets, and evaluation scripts.

Aayam Bansal

IEEE

VLM Hallucination Mitigation VLM Evaluation Neuro-Symbolic AI

Feb 17, 2026

Can Vision-Language Models See Squares? Text-Recognition Mediates Spatial Reasoning Across Three Model Families

We present a simple experiment that exposes a fundamental limitation in vision-language models (VLMs): the inability to accurately localize filled cells in binary grids when those cells lack textual identity. We generate fifteen 15x15 grids with varying density (10.7%-41.8% filled cells) and render each as two image types -- text symbols (. and #) and filled squares without gridlines -- then ask three frontier VLMs (Claude Opus, ChatGPT 5.2, and Gemini 3 Thinking) to transcribe them. In the text-symbol condition, Claude and ChatGPT achieve approximately 91% cell accuracy and 84% F1, while Gemini achieves 84% accuracy and 63% F1. In the filled-squares condition, all three models collapse to 60-73% accuracy and 29-39% F1. Critically, all conditions pass through the same visual encoder -- the text symbols are images, not tokenized text. The text-vs-squares F1 gap ranges from 34 to 54 points across models, demonstrating that VLMs behave as if they possess a high-fidelity text-recognition pathway for spatial reasoning that dramatically outperforms their native visual pathway. Each model exhibits a distinct failure mode in the squares condition -- systematic under-counting (Claude), massive over-counting (ChatGPT), and template hallucination (Gemini) -- but all share the same underlying deficit: severely degraded spatial localization for non-textual visual elements.

Yuval Levental

Rochester Institute of Technology

Vision-Language Models VLM Reasoning VLM Evaluation Spatial Reasoning in Language Models Modality Gap in VLMs

Feb 16, 2026

ThermEval: A Structured Benchmark for Evaluation of Vision-Language Models on Thermal Imagery

Vision language models (VLMs) achieve strong performance on RGB imagery, but they do not generalize to thermal images. Thermal sensing plays a critical role in settings where visible light fails, including nighttime surveillance, search and rescue, autonomous driving, and medical screening. Unlike RGB imagery, thermal images encode physical temperature rather than color or texture, requiring perceptual and reasoning capabilities that existing RGB-centric benchmarks do not evaluate. We introduce ThermEval-B, a structured benchmark of approximately 55,000 thermal visual question answering pairs designed to assess the foundational primitives required for thermal vision language understanding. ThermEval-B integrates public datasets with our newly collected ThermEval-D, the first dataset to provide dense per-pixel temperature maps with semantic body-part annotations across diverse indoor and outdoor environments. Evaluating 25 open-source and closed-source VLMs, we find that models consistently fail at temperature-grounded reasoning, degrade under colormap transformations, and default to language priors or fixed responses, with only marginal gains from prompting or supervised fine-tuning. These results demonstrate that thermal understanding requires dedicated evaluation beyond RGB-centric assumptions, positioning ThermEval as a benchmark to drive progress in thermal vision language modeling.

Ayush Shrivastava, Kirtan Gangani, Laksh Jain +2

Indian Institute of Technology, Gandhinagar, India · Carnegie Mellon University, Pittsburgh, USA

VLM Evaluation Thermal Imaging Visual Question Answering VLM Robustness

Feb 16, 2026

Error Patterns in Historical OCR: A Comparative Analysis of TrOCR and a Vision-Language Model

Optical Character Recognition (OCR) of eighteenth-century printed texts remains challenging due to degraded print quality, archaic glyphs, and non-standardized orthography. Although transformer-based OCR systems and Vision-Language Models (VLMs) achieve strong aggregate accuracy, metrics such as Character Error Rate (CER) and Word Error Rate (WER) provide limited insight into their reliability for scholarly use. We compare a dedicated OCR transformer (TrOCR) and a general-purpose Vision-Language Model (Qwen) on line-level historical English texts using length-weighted accuracy metrics and hypothesis driven error analysis. While Qwen achieves lower CER/WER and greater robustness to degraded input, it exhibits selective linguistic regularization and orthographic normalization that may silently alter historically meaningful forms. TrOCR preserves orthographic fidelity more consistently but is more prone to cascading error propagation. Our findings show that architectural inductive biases shape OCR error structure in systematic ways. Models with similar aggregate accuracy can differ substantially in error locality, detectability, and downstream scholarly risk, underscoring the need for architecture-aware evaluation in historical digitization workflows.

Ari Vesalainen, Eetu Mäkelä, Laura Ruotsalainen +1

University of Helsinki, Department of Computer Science, Finland · University of Helsinki, Department of Digital Humanities, Finland

Optical Character Recognition VLM Evaluation

Feb 13, 2026

An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation

Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.g., Mermaid). In production, these systems process arbitrary inputs for which no ground-truth code exists, making output quality difficult to assess. We propose a reference-free evaluation framework that monitors flowchart image-to-code generation quality at inference time, using only the input image and the generated output. The framework introduces two automated metrics:

\text{Recall}{\text{OCR}}

, which estimates content coverage by extracting text from the input image via OCR as a proxy reference, and

\text{Precision}{\text{VE}}

, which detects hallucinated elements through Visual Entailment against the original image. Their harmonic mean,

\text{F1}{\text{OCR-VE}}

, provides a unified quality score. Validation on the FlowVQA dataset shows strong agreement with ground-truth metrics (average Pearson's

r = 0.97

,

0.91

, and

0.94

for Recall, Precision, and F1, respectively), confirming the framework's reliability as a practical, reference-free alternative for continuous quality monitoring in production settings.

Giang Son Nguyen, Zi Pong Lim, Sarthak Ketanbhai Modi +2

Nanyang Technological University · VinUniversity · AUMOVIO Singapore

VLM Evaluation Code Generation Reference-Free Evaluation Automated Evaluation Image-to-Code Generation

Feb 11, 2026

VideoSTF: Stress-Testing Output Repetition in Video Large Language Models

Video Large Language Models (VideoLLMs) have achieved strong performance on video understanding tasks, yet existing benchmarks evaluate only what models predict, leaving the stability of how they generate largely unexamined. We surface a previously underexplored generation failure of VideoLLMs, defined as output repetition, in which the decoder collapses into self-reinforcing loops of repeated phrases or sentences, and present VideoSTF, a benchmarking framework for systematically measuring, stress-testing, and exploiting this failure mode. VideoSTF formalizes repetition with three complementary

n

-gram-based metrics, ships a standardized testbed of 10,000 diverse videos, and provides a library of controlled temporal stressors. Across 10 advanced VideoLLMs, VideoSTF reveals four key findings: (i) repetition is pervasive on unperturbed videos and stable across commonly used frame counts, with repetition rates up to 91%; (ii) it spans a severity spectrum from mild redundancy to token-cap loops, and is highly amplified by temporal perturbations; (iii) temporal stressors form a practical black-box attack surface, flipping benign videos into repetitive ones with tens of queries and high attack success rates (up to 98%), and (iv) repetition is not explained by visual redundancy, its amplification tracks local temporal disruption, and only repetition penalties reduce it among common mitigations such as top-

k

sampling, input filtering, and prompt variation, but increasing the penalty weakens visual grounding. VideoSTF reframes generation stability as a useful and complementary evaluation axis for VideoLLMs and provides the tools to study it. The project page is available at https://videostf.github.io/.

Yuxin Cao, Wei Song, Shangzhi Xu +2

National University of Singapore, Singapore · University of New South Wales, Australia · CSIRO’s Data61, Australia

VLM Evaluation VLM Robustness Video-Language Models

Feb 10, 2026

Egocentric Bias in Vision-Language Models

Visual perspective taking--inferring how the world appears from another's viewpoint--is foundational to social cognition. We introduce FlipSet, a diagnostic benchmark for Level-2 visual perspective taking (L2 VPT) in vision-language models. The task requires simulating 180-degree rotations of 2D character strings from another agent's perspective, isolating spatial transformation from 3D scene complexity. Evaluating 103 VLMs reveals systematic egocentric bias: the vast majority perform below chance, with roughly three-quarters of errors reproducing the camera viewpoint. Control experiments expose a compositional deficit--models achieve high theory-of-mind accuracy and above-chance mental rotation in isolation, yet fail catastrophically when integration is required. This dissociation indicates that current VLMs lack the mechanisms needed to bind social awareness to spatial operations, suggesting fundamental limitations in model-based spatial reasoning. FlipSet provides a cognitively grounded testbed for diagnosing perspective-taking capabilities in multimodal systems.

Maijunxian Wang, Yijiang Li, Bingyang Wang +6

Cognitive Science Program, University of California, Berkeley · Department of Electrical and Computer Engineering, University of California San Diego · School of Computer Science, Georgia Institute of Technology & Emory University +6

VLM Evaluation Visual Spatial Reasoning Visual Reasoning VLM Reasoning

Feb 8, 2026

Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures

Facial age estimation plays a critical role in content moderation, age verification, and deepfake detection. However, no prior benchmark has systematically compared modern vision-language models (VLMs) with specialized age estimation architectures. We present the first large-scale cross-paradigm benchmark, evaluating 34 models - 22 specialized architectures with publicly available pretrained weights and 12 general-purpose VLMs - across eight standard datasets (UTKFace, IMDB-WIKI, MORPH, AFAD, CACD, FG-NET, APPA-REAL, and AgeDB), totaling 1,100 test images per model. Our key finding is striking: zero-shot VLMs significantly outperform most specialized models, achieving an average mean absolute error (MAE) of 5.65 years compared to 9.88 years for non-LLM models. The best-performing VLM (Gemini 3 Flash Preview, MAE 4.32) surpasses the strongest non-LLM model (MiVOLO, MAE 5.10) by 15%. MiVOLO - unique in combining face and body features using Vision Transformers - is the only specialized model that remains competitive with VLMs. We further analyze age verification at the 18-year threshold and find that most non-LLM models exhibit false adult rates between 39% and 100% for minors, whereas VLMs reduce this to 16%-29%. Additionally, coarse age binning (8-9 classes) consistently increases MAE beyond 13 years. Stratified analysis across 14 age groups reveals that all models struggle most at extreme ages (under 5 and over 65). Overall, these findings challenge the assumption that task-specific architectures are necessary for high-performance age estimation and suggest that future work should focus on distilling VLM capabilities into efficient specialized models.

Simiao Ren, Xingyu Shen, Ankit Raj +8

Manlin · Reality Inc. · New York University +2

Large Vision-Language Models VLM Evaluation

Feb 6, 2026

Same Answer, Different Representations: Hidden instability in VLMs

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is insufficient. We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness (spatial consistency of vision tokens), alongside standard label-based metrics. Applying this framework to modern VLMs across the SEEDBench, MMMU, and POPE datasets reveals three distinct failure modes. First, models frequently preserve predicted answers while undergoing substantial internal representation drift; for perturbations such as text overlays, this drift approaches the magnitude of inter-image variability, indicating that representations move to regions typically occupied by unrelated inputs despite unchanged outputs. Second, robustness does not improve with scale; larger models achieve higher accuracy but exhibit equal or greater sensitivity, consistent with sharper yet more fragile decision boundaries. Third, we find that perturbations affect tasks differently: they harm reasoning when they disrupt how models combine coarse and fine visual cues, but on the hallucination benchmarks, they can reduce false positives by making models generate more conservative answers.

Farooq Ahmad Wani, Alessandro Suglia, Rohit Saxena +6

Sapienza University of Rome · University of Edinburgh · University of Oxford +5

VLM Evaluation VLM Robustness Vision-Language Models Neural Network Robustness Adversarial Robustness Representation Geometry in VLMs

Feb 5, 2026

VRIQ: Benchmarking and Diagnosing the Visual-Reasoning IQ of Vision-Language Models

Vision-language model (VLM) errors on visual reasoning may come from missing visual structure, from mistakes after that structure is extracted, or from both. We introduce VRIQ, a benchmark of 1,391 human-verified IQ-style visual reasoning puzzles spanning five psychometric categories, each instantiated in category-matched abstract and natural-image domains. To study perception and reasoning more directly, we also introduce DiagVRIQ, a 209-item diagnostic subset paired with human-verified, rule-neutral textual descriptions. Across 21 VLMs, the 17 non-frontier models reach a 26.8% unweighted category mean on abstract puzzles, while three 2026 frontier models improve substantially but unevenly, with unweighted category means of 41.3--70.9% on abstract puzzles and at most 78.2% on natural-image puzzles; all remain below human performance. On DiagVRIQ, even when their descriptions are judged correct, the strongest models still answer approximately 9--12% of those items incorrectly. Two interventions, ground-truth description augmentation and tool-augmented inference, improve accuracy, with the largest tool gains on spatially demanding categories, but neither eliminates errors. VRIQ and DiagVRIQ provide a framework for studying visual reasoning through complementary end-to-end, description-based, and intervention-based analyses rather than treating it as a single monolithic capability.

Tina Khezresmaeilzadeh, Jike Zhong, Konstantinos Psounis

University of Southern California, Los Angeles, USA

Visual Reasoning VLM Reasoning VLM Evaluation

Feb 1, 2026

Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters

Digital video is central to communication, education, and entertainment, but without audio description (AD), blind and low-vision users are excluded. While crowdsourced platforms and vision-language models (VLMs) expand AD production, quality is rarely checked systematically. Existing evaluations rely on NLP metrics and short-clip guidelines, leaving open the question of how to assess long-form AD quality at scale. To address this, we developed a methodological workflow using Item Response Theory to evaluate VLM and human rater proficiency against expert-established ground truth. Evaluations were based on a six-dimensional framework, grounded in professional guidelines and shaped by insights from our accessibility experts and blind consultants. Findings suggest that top-performing VLMs can approximate ground-truth ratings at levels comparable to human raters. However, qualitative analysis reveals that VLM reasoning is less reliable and actionable than that of human respondents. These insights underscore the potential of hybrid evaluation systems that leverage VLMs alongside human oversight, offering a path toward scalable AD quality control.

Lana Do, Gio Jung, Juvenal Francisco Barajas +5

Northeastern University · United States · San Francisco State University +2

VLM Evaluation Human-in-the-Loop Evaluation

Feb 1, 2026

Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance

While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often infeasible due to computational constraints and data limitations in few shot scenarios. Existing selection methods fail to fully address this: they either rely on data-intensive proxies or use symmetric textual descriptors that neglect the inherently directional and model-specific nature of transferability. To address this problem, we propose a framework that grounds model selection in the internal functional dynamics of the visual encoder. Our approach represents each task via layer wise conductance and derives a target-conditioned block importance distribution through entropy regularized alignment. Building on this, we introduce Directional Conductance Divergence (DCD), an asymmetric metric that quantifies how effectively a source task covers the target's salient functional blocks. This allows for predicting target model rankings by aggregating source task ranks without direct inference. Experimental results on 48 VLMs across 21 datasets demonstrate that our method outperforms state-of-the-art baselines, achieving a 14.7% improvement in NDCG@5 over SWAB.

Wei Yang, Hong Xie, Tao Tan +3

School of AI and Data Science USTC

VLM Evaluation Vision-Language Models Task Transferability Estimation Transfer Learning

Jan 30, 2026

TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs

Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) master static semantics, their grasp of temporal dynamics remains brittle. We present TimeBlind, a diagnostic benchmark for compositional spatio-temporal understanding. Inspired by cognitive science, TimeBlind categorizes fine-grained temporal understanding into three levels: recognizing atomic events, characterizing event properties, and reasoning about event interdependencies. Unlike benchmarks that conflate recognition with temporal reasoning, TimeBlind leverages a minimal-pairs paradigm: video pairs share identical static visual content but differ solely in temporal structure, utilizing complementary questions to neutralize language priors. Evaluating over 20 state-of-the-art MLLMs (e.g., GPT-5, Gemini 3 Pro) on 600 curated instances (2400 video-question pairs), reveals that the Instance Accuracy (correctly distinguishing both videos in a pair) of the best performing MLLM is only 48.2%, far below the human performance (98.2%). These results demonstrate that even frontier models rely heavily on static visual shortcuts rather than genuine temporal logic, positioning TimeBlind as a vital diagnostic tool for next-generation video understanding. Dataset and code are available at https://baiqi-li.github.io/timeblind_project/ .

Baiqi Li, Kangyi Zhao, Ce Zhang +3

University of North Carolina at Chapel Hill · University of Pittsburgh · Carnegie Mellon University

VLM Evaluation Video Understanding Multimodal Large Language Models Video Reasoning Temporal Video Understanding Multimodal Understanding

Jan 30, 2026

A Comparative Evaluation of Large Vision-Language Models for 2D Object Detection under SOTIF Conditions

Reliable environmental perception remains one of the main obstacles for safe operation of automated vehicles. Safety of the Intended Functionality (SOTIF) concerns safety risks from perception insufficiencies, particularly under adverse conditions where conventional detectors often falter. While Large Vision-Language Models (LVLMs) demonstrate promising semantic reasoning, their quantitative effectiveness for safety-critical 2D object detection is underexplored. This paper presents a systematic evaluation of ten representative LVLMs using the PeSOTIF dataset, a benchmark specifically curated for long-tail traffic scenarios and environmental degradations. Performance is quantitatively compared against two specialized detectors: the anchor-based YOLOv5 and the transformer-based RT-DETRv4. Experimental results reveal a critical trade-off: top-performing LVLMs (e.g., Gemini 3) surpass the YOLOv5 in recall by over 25% and closely match RT-DETRv4 under natural visual degradation, while specialized detectors retain an advantage in geometric precision for handcrafted perturbations. These findings highlight the complementary strengths of semantic reasoning versus geometric regression, supporting the use of LVLMs as high-level safety validators in SOTIF-oriented automated driving systems.

Ji Zhou, Yilin Ding, Yongqi Zhao +4

Institute of Automotive Engineering, Graz University of Technology, 8010 Graz, Austria · Independent Researcher, 200000 Shanghai, China · School of Intelligent Connected Vehicle, Hubei University of Automotive Technology, 442002 Shiyan, China +1

VLM Evaluation Large Vision-Language Models Autonomous Driving Perception Object Detection

Jan 26, 2026

DisasterInsight: A Building-Centric Benchmark for Evaluating Vision--Language Models in Disaster Response

Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-centric assessment. To study this building-centric gap, we introduce \method{}, a diagnostic benchmark built on xBD, a pre/post-disaster satellite dataset with building-level damage labels. \method{} enriches building instances with OpenStreetMap-derived functional labels and contains 134{,}108 task-specific instruction records across 15 task types, spanning instance-level assessment, scene-level counting, multi-instance reasoning, and structured report generation. The benchmark supports RGB pre/post-disaster imagery, single- and multi-view instance formulations, and scene-level RGB/SAR diagnostic inputs. Experiments with general-domain and remote-sensing VLMs show that models perform better on visible damage cues than on building-function understanding, multi-instance reasoning, counting, and grounded reporting. Instruction tuning improves performance on several tasks but does not close this building-centric gap.

Sara Tehrani, Yonghao Xu, Leif Haglund +3

Computer Vision and Learning System, Linköping University, Sweden · Vantor, Linköping, Sweden

Building Damage Assessment Remote Sensing Image Understanding Disaster Damage Assessment VLM Evaluation Remote Sensing Benchmarks Disaster Response+1

Jan 13, 2026

Semantic Misalignment in Vision-Language Models under Perceptual Degradation

Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for safe semantic reasoning and decision-making. While recent VLMs demonstrate strong performance on multimodal benchmarks, their robustness to realistic perception degradation remains poorly understood. In this work, we systematically study semantic misalignment in VLMs under controlled degradation of upstream visual perception, using semantic segmentation on the Cityscapes dataset as a representative perception module. We introduce perception-realistic corruptions that induce only moderate drops in conventional segmentation metrics, yet observe severe failures in downstream VLM behavior, including hallucinated object mentions, omission of safety-critical entities, and inconsistent safety judgments. To quantify these effects, we propose a set of language-level misalignment metrics that capture hallucination, critical omission, and safety misinterpretation, and analyze their relationship with segmentation quality across multiple contrastive and generative VLMs. Our results reveal a clear disconnect between pixel-level robustness and multimodal semantic reliability, highlighting a critical limitation of current VLM-based systems and motivating the need for evaluation frameworks that explicitly account for perception uncertainty in safety-critical applications.

Guo Cheng, Huang Li

VLM Evaluation VLM Robustness Object Hallucination in VLMs Autonomous Driving Perception

Jan 10, 2026

BabyVision: Visual Reasoning Beyond Language

While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.

Liang Chen, Weichu Xie, Yiyan Liang +27

1UniPat AI · 6Peking University · 3Alibaba Group +8

VLM Evaluation Visual Reasoning Multimodal Large Language Models Modality Gap in VLMs Visually Grounded Reasoning Multimodal Foundation Models+1

Jan 8, 2026

SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models

Automatic identification of events and recurrent behavior analysis are critical for video surveillance. However, most existing content-based video retrieval benchmarks focus on scene-level similarity and do not evaluate the action discrimination required in surveillance. To address this gap, we introduce SOVABench (Surveillance Opposite Vehicle Actions Benchmark), a real-world retrieval benchmark built from surveillance footage and centered on vehicle-related actions. SOVABench defines two evaluation protocols (inter-pair and intra-pair) to assess cross-action discrimination and temporal direction understanding. Although action distinctions are generally intuitive for human observers, our experiments show that they remain challenging for state-of-the-art vision and multimodal models. Leveraging the visual reasoning and instruction-following capabilities of Multimodal Large Language Models (MLLMs), we present a training-free framework for producing interpretable embeddings from MLLM-generated descriptions for both images and videos. The framework achieves strong performance on SOVABench as well as on several spatial and counting benchmarks where contrastive Vision-Language Models often fail. The code, annotations, and instructions to construct the benchmark are publicly available.

Oriol Rabasseda, Zenjie Li, Kamal Nasrollahi +1

Universitat de Barcelona and Computer Vision Center Gran Via de les Corts Catalanes 585, Barcelona Campus UAB, Edifici O, Cerdanyola del Vall`es · Milestone Systems A/S Banemarksvej 50, Brøndby · Aalborg Universitet Fredrik Bajers Vej 7K, Aalborg Øst

Video Retrieval VLM Evaluation Temporal Video Understanding